{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-radial-kernel-networks-approximating","title":"Deep Radial Kernel Networks: Approximating Radially Symmetric Functions with Deep Networks","arxiv_id":"1703.03470","date":"2017-03-09","proceeding":null,"authors":["Brendan McCane","Lech Szymanski"],"abstract":"We prove that a particular deep network architecture is more efficient at\napproximating radially symmetric functions than the best known 2 or 3 layer\nnetworks. We use this architecture to approximate Gaussian kernel SVMs, and\nsubsequently improve upon them with further training. The architecture and\ninitial weights of the Deep Radial Kernel Network are completely specified by\nthe SVM and therefore sidesteps the problem of empirically choosing an\nappropriate deep network architecture.","url_abs":"http://arxiv.org/abs/1703.03470v1","url_pdf":"http://arxiv.org/pdf/1703.03470v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-radial-kernel-networks-approximating","repo_url":"https://bitbucket.org/mccane/deep-radial-kernel-network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}